yyzpiero / RL4RedTeam
A PPO agent leveraging reinforcement learning performs Penetration Testing in a simulated computer network environment. The agent is trained to scan for vulnerabilities in the network and exploit them to gain access to various network resources.
☆23Updated last year
Related projects ⓘ
Alternatives and complementary repositories for RL4RedTeam
- Gym-based environment for training offensive RL agents. Agents can generalize to unseen scenarios and simulation-trained agents can be de…☆33Updated 2 months ago
- PenGym: Pentesting Training Framework for Reinforcement Learning Agents☆22Updated last month
- Deep RL agents for NASimEmu. See also https://github.com/jaromiru/NASimEmu.☆13Updated 4 months ago
- An environment for testing AI pentesting agents against a simulated network.☆169Updated 8 months ago
- Multi-Agent Reinforcement Learning on network-security☆16Updated 2 years ago
- ☆17Updated 2 years ago
- An Abstract Cyber Security Simulation and Markov Game for OpenAI Gym☆74Updated last year
- ☆51Updated last year
- YAWNING TITAN is an abstract, graph based cyber-security simulation environment that supports the training of intelligent agents for auto…☆58Updated 6 months ago
- Cyber Operations Research Gym☆63Updated 5 months ago
- The TTCP CAGE Challenges are a series of public challenges instigated to foster the development of autonomous cyber defensive agents. Thi…☆41Updated 3 months ago
- Modelling Capture-the-Flag Challenges Using Reinforcement Learning☆15Updated 2 years ago
- A Simulated Optimal Intrusion Response Game☆21Updated 2 years ago
- An environment simulation for networks security tasks for development and testing AI based agents. Part of AI Dojo project☆39Updated this week
- A research platform to develop automated security policies using quantitative methods, e.g., optimal control, computational game theory, …☆119Updated 2 months ago
- A library to produce cybersecurity exploitation routes (exploit flows). Inspired by TensorFlow.☆29Updated last year
- TTCP CAGE Challenge 2☆46Updated 5 months ago
- ☆22Updated last month
- TTCP CAGE Challenge 3☆34Updated 7 months ago
- A comprehensive local Linux Privilege-Escalation Benchmark☆24Updated 3 weeks ago
- This is a dataset intended to train a LLM model for a completely CVE focused input and output.☆44Updated last week
- ☆63Updated this week
- [NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"☆61Updated 3 months ago
- Modelling SQL Injection Using Reinforcement Learning☆19Updated 3 years ago
- ☆36Updated this week
- AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks☆28Updated 5 months ago
- A collection of agents that use Large Language Models (LLMs) to perform tasks common on our day to day jobs in cyber security.☆56Updated 6 months ago
- ☆10Updated 2 months ago
- AI-enabled Cybersecurity for Future Smart Environments☆19Updated 3 months ago
- Payloads for Attacking Large Language Models☆64Updated 4 months ago